Friday, Nov 13 | --:--
Times of AI

Regions

China Europe India Japan Taiwan United Kingdom United States

Platforms

Alibaba Qwen Amazon Anthropic DeepMind Google Groq Meta Microsoft MiniMax Mistral Moonshot AI NVIDIA OpenAI PrismML Replit Thinking Machines xAI

Sections

Business Engineering Enterprise Frontier Labs Hardware Industry Infrastructure Models Policy Products Research Safety Security Work All articles → Subscribe by email
Back to home
Products Developer Tools United States Anthropic

Claude Code Routines: Agentic Coding Leaves the Always-On Laptop

Anthropic’s Claude Code Routines (research preview) run saved prompts + GitHub repos + connectors on Anthropic cloud — cron, API/webhook, or GitHub events — so agents wake, work, and sleep without a local machine. Paired with desktop/web redesign (multi-session, parallel agents). Preview quotas apply; outputs still need human review.

Times of AI Desk 6 min read San Francisco View as Markdown
Illustration of Claude Code Routines running on cloud servers: a sleeping laptop on a desk beside an active cloud icon with scheduled cron, GitHub PR, and API webhook triggers firing autonomous Claude agents that edit code repositories, dated April 14 2026 research preview

Interactive coding agents still assume a human session. Routines’ trade: infra-less background automation — Anthropic hosts the wake/sleep cycle — so nightly reviews and webhook responders stop depending on a glowing laptop.

Anthropic (April 14) launched Claude Code Routines in research preview for Pro, Max, Team, and Enterprise. A Routine packages a prompt, GitHub repo(s), and connectors; triggers include cron-like schedules, API/webhook calls (POST to /fire with beta header experimental-cc-routine-2026-04-01), or GitHub events (e.g. pull_request.opened, issues). Execution on Anthropic-managed cloud — no local always-on requirement. Configure via claude.ai/code/routines, desktop app, or CLI (/schedule). Plan-based daily run caps.

Ships with Claude Code desktop/web redesign: multi-session sidebar, integrated terminal, parallel agents, faster diff viewer (contemporaneous coverage, e.g. 9to5Mac).

How a run works#

  1. Trigger fires.
  2. Agent wakes in cloud with prompt + repo/tool context.
  3. Reads/edits/runs commands via connected tools.
  4. Diffs/logs/outputs surface in UI or notifications.
  5. Session ends until next trigger.

Example jobs cited in docs/coverage: nightly review/labeling, Sentry/monitor webhooks, scheduled refactors/tests/deps, CI-adjacent GitHub activity — illustrative, not SLAs.

Claims vs checks#

Feature mechanics and preview status are Anthropic docs primary. “Reliable always-available agentic coding infrastructure” is aspiration. Early user reports confirm cloud execution model; they do not prove correctness or security of unattended edits.

Limits#

  • Research preview: quotas, evolving APIs, beta headers.
  • Best for scoped/repeatable tasks — not open-ended autonomy guarantees.
  • Human review still required for correctness and security.
  • Cost/monitoring controls are operator problems Anthropic only partially productizes here.

Sources#

Related Coverage

Scroll to continue reading